agent-routines

Use this skill for backend API, DTO, or enum changes that require frontend request wrappers, types, enums, or UI adaptations.

Use this skill for durable execution records, runbooks, evidence folders, artifacts, and validation of archive layout after task completion.

Use this skill for validated local commit and optional push workflows where scope, staged content, identity, gates, and human confirmation must be handled explicitly.

Use this skill for desktop productivity UI design systems, design tokens, dense tables, status markers, theme tokens, and non-AI-looking Electron app visual standards.

Use this skill for Electron desktop packaging and release readiness across Windows, macOS, and Linux, including signing boundaries, artifacts, dry-runs, and public release checks.

Use this skill for cross-platform desktop UI QA of Electron apps, including renderer screenshots, native window behavior, shell prerequisites, task logs, and platform-specific checks.

Use this skill for database repair work that must begin with readonly confirmation, prepare minimal SQL for human DMS execution, and verify with readonly post-checks.

Use this skill for Electron desktop app implementation with secure main/preload/renderer boundaries, allowlisted IPC, local command execution, themes, i18n, and cross-platform behavior.

Use this skill for cross-platform environment, dependency, shell, PATH, and toolchain audits that must stay readonly unless changes are explicitly authorized.

Use this skill for GitHub Actions, required checks, branch ruleset, and pull request protection planning based on repository evidence.

Use this skill for source-first repository governance audits that must separate current evidence from archived docs, historical context, assumptions, and command output.

Use this skill for codebase graph and MCP readiness checks where indexing scope, project names, tool availability, and fallback discovery must be explicit.

Use this skill for governed repository code changes when local rules, branch state, risk gates, minimal edits, and verification must be handled before summarizing.

Use this skill for Simplified Chinese and English UI localization checks, translation keys, text expansion, status label stability, and language-switch QA.

Use this skill for Java Maven verification where module scope, PowerShell argument quoting, user Maven mirrors, and targeted tests must be handled explicitly.

Use this skill for checking whether Markdown knowledge, documentation, generated stubs, or evidence packs still match current source paths and policies.

Use this skill for merge conflict resolution where both sides must be understood, intended behavior preserved, conflict markers removed, and path-limited validation run.

Use this skill for Node, npm, pnpm, workspace, plugin marketplace, and release dry-run workflows that require validation before publishing.

Use this skill for payment, subscription, and configuration documentation that must be Chinese-first, source-backed, structured, and explicit about risks and confirmations.

Use this skill for prompt-only review, repair, and re-review where the prompt must be improved without executing the workflow it describes.

Use this skill for public release readiness checks where package contents, metadata, documentation, dry runs, and publication gates must be verified before publishing.

Use this skill when asked to review current branch changes, fix actionable issues, and repeat review until no new in-scope issues remain.

Use this skill for local agent runtime diagnosis and repair planning involving launch shims, package managers, hook stdin encoding, auto-update state, and version triage.

Use this skill for local security and public-leakage review before commits, releases, or distribution where sensitive values must not be printed.